Abstract
Current OCT devices provide three-dimensional (3D) in-vivo images of the human retina. The resulting very large data sets are difficult to manually assess. Automated segmentation is required to automatically process the data and produce images that are clinically useful and easy to interpret. In this paper, we present a method to segment the retinal layers in these images. Instead of using complex heuristics to define each layer, simple features are defined and machine learning classifiers are trained based on manually labeled examples. When applied to new data, these classifiers produce labels for every pixel. After regularization of the 3D labeled volume to produce a surface, this results in consistent, three-dimensionally segmented layers that match known retinal morphology. Six labels were defined, corresponding to the following layers: Vitreous, retinal nerve fiber layer (RNFL), ganglion cell layer & inner plexiform layer, inner nuclear layer & outer plexiform layer, photoreceptors & retinal pigment epithelium and choroid. For both normal and glaucomatous eyes that were imaged with a Spectralis (Heidelberg Engineering) OCT system, the five resulting interfaces were compared between automatic and manual segmentation. RMS errors for the top and bottom of the retina were between 4 and 6 μm, while the errors for intra-retinal interfaces were between 6 and 15 μm. The resulting total retinal thickness maps corresponded with known retinal morphology. RNFL thickness maps were compared to GDx (Carl Zeiss Meditec) thickness maps. Both maps were mostly consistent but local defects were better visualized in OCT-derived thickness maps.
Highlights
Current spectral domain Optical Coherence Tomography (OCT), as implemented by various manufacturers for ophthalmic applications, produces high quality data at a high speed
27 May 2011 1 June 2011 / Vol 2, No 6 / BIOMEDICAL OPTICS EXPRESS 1744 umes may be produced with increased signal-to-noise ratio and reduced speckle due to averaging, while the acquisition time is just a few minutes, even in pathological eyes
We present a method for three-dimensional retinal layer segmentation in OCT images by a flexible method that learns from provided examples
Summary
Current spectral domain Optical Coherence Tomography (OCT), as implemented by various manufacturers for ophthalmic applications, produces high quality data at a high speed. Around 15,000–40,000 A-lines (depth scans at a single location) are produced per second. This high speed enables the acquisition of three-dimensional or volumetric data sets in a short period of time [?]. Sampling a volume results in large data sets (in the order of 50 million pixels) which are difficult to quickly analyze in a clinical setting. While the data contains a large amount of information, often much of it is irrelevant for the specific task at hand, such as glaucoma detection or monitoring. Reducing the data to a much smaller and easier to interpret set, still containing most relevant information, is vital for routine clinical use. Reducing the data is required for most tasks related to computer-aided diagnosis
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
